447 lines
8.6 KiB
JavaScript
447 lines
8.6 KiB
JavaScript
|
/**
|
||
|
* @param {string} value
|
||
|
* @returns {RegExp}
|
||
|
* */
|
||
|
|
||
|
/**
|
||
|
* @param {RegExp | string } re
|
||
|
* @returns {string}
|
||
|
*/
|
||
|
function source(re) {
|
||
|
if (!re) return null;
|
||
|
if (typeof re === "string") return re;
|
||
|
|
||
|
return re.source;
|
||
|
}
|
||
|
|
||
|
/**
|
||
|
* @param {RegExp | string } re
|
||
|
* @returns {string}
|
||
|
*/
|
||
|
function lookahead(re) {
|
||
|
return concat('(?=', re, ')');
|
||
|
}
|
||
|
|
||
|
/**
|
||
|
* @param {...(RegExp | string) } args
|
||
|
* @returns {string}
|
||
|
*/
|
||
|
function concat(...args) {
|
||
|
const joined = args.map((x) => source(x)).join("");
|
||
|
return joined;
|
||
|
}
|
||
|
|
||
|
/*
|
||
|
Language: Python
|
||
|
Description: Python is an interpreted, object-oriented, high-level programming language with dynamic semantics.
|
||
|
Website: https://www.python.org
|
||
|
Category: common
|
||
|
*/
|
||
|
|
||
|
function python(hljs) {
|
||
|
const RESERVED_WORDS = [
|
||
|
'and',
|
||
|
'as',
|
||
|
'assert',
|
||
|
'async',
|
||
|
'await',
|
||
|
'break',
|
||
|
'class',
|
||
|
'continue',
|
||
|
'def',
|
||
|
'del',
|
||
|
'elif',
|
||
|
'else',
|
||
|
'except',
|
||
|
'finally',
|
||
|
'for',
|
||
|
'from',
|
||
|
'global',
|
||
|
'if',
|
||
|
'import',
|
||
|
'in',
|
||
|
'is',
|
||
|
'lambda',
|
||
|
'nonlocal|10',
|
||
|
'not',
|
||
|
'or',
|
||
|
'pass',
|
||
|
'raise',
|
||
|
'return',
|
||
|
'try',
|
||
|
'while',
|
||
|
'with',
|
||
|
'yield'
|
||
|
];
|
||
|
|
||
|
const BUILT_INS = [
|
||
|
'__import__',
|
||
|
'abs',
|
||
|
'all',
|
||
|
'any',
|
||
|
'ascii',
|
||
|
'bin',
|
||
|
'bool',
|
||
|
'breakpoint',
|
||
|
'bytearray',
|
||
|
'bytes',
|
||
|
'callable',
|
||
|
'chr',
|
||
|
'classmethod',
|
||
|
'compile',
|
||
|
'complex',
|
||
|
'delattr',
|
||
|
'dict',
|
||
|
'dir',
|
||
|
'divmod',
|
||
|
'enumerate',
|
||
|
'eval',
|
||
|
'exec',
|
||
|
'filter',
|
||
|
'float',
|
||
|
'format',
|
||
|
'frozenset',
|
||
|
'getattr',
|
||
|
'globals',
|
||
|
'hasattr',
|
||
|
'hash',
|
||
|
'help',
|
||
|
'hex',
|
||
|
'id',
|
||
|
'input',
|
||
|
'int',
|
||
|
'isinstance',
|
||
|
'issubclass',
|
||
|
'iter',
|
||
|
'len',
|
||
|
'list',
|
||
|
'locals',
|
||
|
'map',
|
||
|
'max',
|
||
|
'memoryview',
|
||
|
'min',
|
||
|
'next',
|
||
|
'object',
|
||
|
'oct',
|
||
|
'open',
|
||
|
'ord',
|
||
|
'pow',
|
||
|
'print',
|
||
|
'property',
|
||
|
'range',
|
||
|
'repr',
|
||
|
'reversed',
|
||
|
'round',
|
||
|
'set',
|
||
|
'setattr',
|
||
|
'slice',
|
||
|
'sorted',
|
||
|
'staticmethod',
|
||
|
'str',
|
||
|
'sum',
|
||
|
'super',
|
||
|
'tuple',
|
||
|
'type',
|
||
|
'vars',
|
||
|
'zip'
|
||
|
];
|
||
|
|
||
|
const LITERALS = [
|
||
|
'__debug__',
|
||
|
'Ellipsis',
|
||
|
'False',
|
||
|
'None',
|
||
|
'NotImplemented',
|
||
|
'True'
|
||
|
];
|
||
|
|
||
|
// https://docs.python.org/3/library/typing.html
|
||
|
// TODO: Could these be supplemented by a CamelCase matcher in certain
|
||
|
// contexts, leaving these remaining only for relevance hinting?
|
||
|
const TYPES = [
|
||
|
"Any",
|
||
|
"Callable",
|
||
|
"Coroutine",
|
||
|
"Dict",
|
||
|
"List",
|
||
|
"Literal",
|
||
|
"Generic",
|
||
|
"Optional",
|
||
|
"Sequence",
|
||
|
"Set",
|
||
|
"Tuple",
|
||
|
"Type",
|
||
|
"Union"
|
||
|
];
|
||
|
|
||
|
const KEYWORDS = {
|
||
|
$pattern: /[A-Za-z]\w+|__\w+__/,
|
||
|
keyword: RESERVED_WORDS,
|
||
|
built_in: BUILT_INS,
|
||
|
literal: LITERALS,
|
||
|
type: TYPES
|
||
|
};
|
||
|
|
||
|
const PROMPT = {
|
||
|
className: 'meta',
|
||
|
begin: /^(>>>|\.\.\.) /
|
||
|
};
|
||
|
|
||
|
const SUBST = {
|
||
|
className: 'subst',
|
||
|
begin: /\{/,
|
||
|
end: /\}/,
|
||
|
keywords: KEYWORDS,
|
||
|
illegal: /#/
|
||
|
};
|
||
|
|
||
|
const LITERAL_BRACKET = {
|
||
|
begin: /\{\{/,
|
||
|
relevance: 0
|
||
|
};
|
||
|
|
||
|
const STRING = {
|
||
|
className: 'string',
|
||
|
contains: [ hljs.BACKSLASH_ESCAPE ],
|
||
|
variants: [
|
||
|
{
|
||
|
begin: /([uU]|[bB]|[rR]|[bB][rR]|[rR][bB])?'''/,
|
||
|
end: /'''/,
|
||
|
contains: [
|
||
|
hljs.BACKSLASH_ESCAPE,
|
||
|
PROMPT
|
||
|
],
|
||
|
relevance: 10
|
||
|
},
|
||
|
{
|
||
|
begin: /([uU]|[bB]|[rR]|[bB][rR]|[rR][bB])?"""/,
|
||
|
end: /"""/,
|
||
|
contains: [
|
||
|
hljs.BACKSLASH_ESCAPE,
|
||
|
PROMPT
|
||
|
],
|
||
|
relevance: 10
|
||
|
},
|
||
|
{
|
||
|
begin: /([fF][rR]|[rR][fF]|[fF])'''/,
|
||
|
end: /'''/,
|
||
|
contains: [
|
||
|
hljs.BACKSLASH_ESCAPE,
|
||
|
PROMPT,
|
||
|
LITERAL_BRACKET,
|
||
|
SUBST
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
begin: /([fF][rR]|[rR][fF]|[fF])"""/,
|
||
|
end: /"""/,
|
||
|
contains: [
|
||
|
hljs.BACKSLASH_ESCAPE,
|
||
|
PROMPT,
|
||
|
LITERAL_BRACKET,
|
||
|
SUBST
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
begin: /([uU]|[rR])'/,
|
||
|
end: /'/,
|
||
|
relevance: 10
|
||
|
},
|
||
|
{
|
||
|
begin: /([uU]|[rR])"/,
|
||
|
end: /"/,
|
||
|
relevance: 10
|
||
|
},
|
||
|
{
|
||
|
begin: /([bB]|[bB][rR]|[rR][bB])'/,
|
||
|
end: /'/
|
||
|
},
|
||
|
{
|
||
|
begin: /([bB]|[bB][rR]|[rR][bB])"/,
|
||
|
end: /"/
|
||
|
},
|
||
|
{
|
||
|
begin: /([fF][rR]|[rR][fF]|[fF])'/,
|
||
|
end: /'/,
|
||
|
contains: [
|
||
|
hljs.BACKSLASH_ESCAPE,
|
||
|
LITERAL_BRACKET,
|
||
|
SUBST
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
begin: /([fF][rR]|[rR][fF]|[fF])"/,
|
||
|
end: /"/,
|
||
|
contains: [
|
||
|
hljs.BACKSLASH_ESCAPE,
|
||
|
LITERAL_BRACKET,
|
||
|
SUBST
|
||
|
]
|
||
|
},
|
||
|
hljs.APOS_STRING_MODE,
|
||
|
hljs.QUOTE_STRING_MODE
|
||
|
]
|
||
|
};
|
||
|
|
||
|
// https://docs.python.org/3.9/reference/lexical_analysis.html#numeric-literals
|
||
|
const digitpart = '[0-9](_?[0-9])*';
|
||
|
const pointfloat = `(\\b(${digitpart}))?\\.(${digitpart})|\\b(${digitpart})\\.`;
|
||
|
const NUMBER = {
|
||
|
className: 'number',
|
||
|
relevance: 0,
|
||
|
variants: [
|
||
|
// exponentfloat, pointfloat
|
||
|
// https://docs.python.org/3.9/reference/lexical_analysis.html#floating-point-literals
|
||
|
// optionally imaginary
|
||
|
// https://docs.python.org/3.9/reference/lexical_analysis.html#imaginary-literals
|
||
|
// Note: no leading \b because floats can start with a decimal point
|
||
|
// and we don't want to mishandle e.g. `fn(.5)`,
|
||
|
// no trailing \b for pointfloat because it can end with a decimal point
|
||
|
// and we don't want to mishandle e.g. `0..hex()`; this should be safe
|
||
|
// because both MUST contain a decimal point and so cannot be confused with
|
||
|
// the interior part of an identifier
|
||
|
{
|
||
|
begin: `(\\b(${digitpart})|(${pointfloat}))[eE][+-]?(${digitpart})[jJ]?\\b`
|
||
|
},
|
||
|
{
|
||
|
begin: `(${pointfloat})[jJ]?`
|
||
|
},
|
||
|
|
||
|
// decinteger, bininteger, octinteger, hexinteger
|
||
|
// https://docs.python.org/3.9/reference/lexical_analysis.html#integer-literals
|
||
|
// optionally "long" in Python 2
|
||
|
// https://docs.python.org/2.7/reference/lexical_analysis.html#integer-and-long-integer-literals
|
||
|
// decinteger is optionally imaginary
|
||
|
// https://docs.python.org/3.9/reference/lexical_analysis.html#imaginary-literals
|
||
|
{
|
||
|
begin: '\\b([1-9](_?[0-9])*|0+(_?0)*)[lLjJ]?\\b'
|
||
|
},
|
||
|
{
|
||
|
begin: '\\b0[bB](_?[01])+[lL]?\\b'
|
||
|
},
|
||
|
{
|
||
|
begin: '\\b0[oO](_?[0-7])+[lL]?\\b'
|
||
|
},
|
||
|
{
|
||
|
begin: '\\b0[xX](_?[0-9a-fA-F])+[lL]?\\b'
|
||
|
},
|
||
|
|
||
|
// imagnumber (digitpart-based)
|
||
|
// https://docs.python.org/3.9/reference/lexical_analysis.html#imaginary-literals
|
||
|
{
|
||
|
begin: `\\b(${digitpart})[jJ]\\b`
|
||
|
}
|
||
|
]
|
||
|
};
|
||
|
const COMMENT_TYPE = {
|
||
|
className: "comment",
|
||
|
begin: lookahead(/# type:/),
|
||
|
end: /$/,
|
||
|
keywords: KEYWORDS,
|
||
|
contains: [
|
||
|
{ // prevent keywords from coloring `type`
|
||
|
begin: /# type:/
|
||
|
},
|
||
|
// comment within a datatype comment includes no keywords
|
||
|
{
|
||
|
begin: /#/,
|
||
|
end: /\b\B/,
|
||
|
endsWithParent: true
|
||
|
}
|
||
|
]
|
||
|
};
|
||
|
const PARAMS = {
|
||
|
className: 'params',
|
||
|
variants: [
|
||
|
// Exclude params in functions without params
|
||
|
{
|
||
|
className: "",
|
||
|
begin: /\(\s*\)/,
|
||
|
skip: true
|
||
|
},
|
||
|
{
|
||
|
begin: /\(/,
|
||
|
end: /\)/,
|
||
|
excludeBegin: true,
|
||
|
excludeEnd: true,
|
||
|
keywords: KEYWORDS,
|
||
|
contains: [
|
||
|
'self',
|
||
|
PROMPT,
|
||
|
NUMBER,
|
||
|
STRING,
|
||
|
hljs.HASH_COMMENT_MODE
|
||
|
]
|
||
|
}
|
||
|
]
|
||
|
};
|
||
|
SUBST.contains = [
|
||
|
STRING,
|
||
|
NUMBER,
|
||
|
PROMPT
|
||
|
];
|
||
|
|
||
|
return {
|
||
|
name: 'Python',
|
||
|
aliases: [
|
||
|
'py',
|
||
|
'gyp',
|
||
|
'ipython'
|
||
|
],
|
||
|
keywords: KEYWORDS,
|
||
|
illegal: /(<\/|->|\?)|=>/,
|
||
|
contains: [
|
||
|
PROMPT,
|
||
|
NUMBER,
|
||
|
{
|
||
|
// very common convention
|
||
|
begin: /\bself\b/
|
||
|
},
|
||
|
{
|
||
|
// eat "if" prior to string so that it won't accidentally be
|
||
|
// labeled as an f-string
|
||
|
beginKeywords: "if",
|
||
|
relevance: 0
|
||
|
},
|
||
|
STRING,
|
||
|
COMMENT_TYPE,
|
||
|
hljs.HASH_COMMENT_MODE,
|
||
|
{
|
||
|
variants: [
|
||
|
{
|
||
|
className: 'function',
|
||
|
beginKeywords: 'def'
|
||
|
},
|
||
|
{
|
||
|
className: 'class',
|
||
|
beginKeywords: 'class'
|
||
|
}
|
||
|
],
|
||
|
end: /:/,
|
||
|
illegal: /[${=;\n,]/,
|
||
|
contains: [
|
||
|
hljs.UNDERSCORE_TITLE_MODE,
|
||
|
PARAMS,
|
||
|
{
|
||
|
begin: /->/,
|
||
|
endsWithParent: true,
|
||
|
keywords: KEYWORDS
|
||
|
}
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
className: 'meta',
|
||
|
begin: /^[\t ]*@/,
|
||
|
end: /(?=#)|$/,
|
||
|
contains: [
|
||
|
NUMBER,
|
||
|
PARAMS,
|
||
|
STRING
|
||
|
]
|
||
|
}
|
||
|
]
|
||
|
};
|
||
|
}
|
||
|
|
||
|
module.exports = python;
|